Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    numerical values and technical codes within text

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and their relationships, particularly regarding age and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.87
    sylv
    -0.73
    ellation
    -0.71
    wcs
    -0.69
    */(
    -0.69
    ãĤ©
    -0.67
    acci
    -0.66
    iatric
    -0.66
    anut
    -0.65
    uously
    -0.65
    POSITIVE LOGITS
    ĸļ
    0.73
    schild
    0.66
    motion
    0.61
    1945
    0.59
     Wonderland
    0.59
    WAY
    0.58
    sup
    0.58
     Banks
    0.58
     privacy
    0.58
     Antarctica
    0.57
    Act Density 0.233%

    No Known Activations